Results 281 to 290 of about 1,980,897 (317)
Some of the next articles are maybe not open access.
Deep Convolutional Neural Nets for Objective Steatosis Detection From Liver Samples
International Conference on Computational Photography, 2017Monica Lupsor Platon, Cristian Vicas
exaly +2 more sources
P–Nets: Deep Polynomial Neural Networks
, 2020 Deep Convolutional Neural Networks (DCNNs) is currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning.
Stylianos Moschoglou +2 more
exaly +2 more sources
Knowledge Transfer in Deep Convolutional Neural Nets
International Journal on Artificial Intelligence Tools, 2008Knowledge transfer is widely held to be a primary mechanism that enables humans to quickly learn new complex concepts when given only small training sets. In this paper, we apply knowledge transfer to deep convolutional neural nets, which we argue are particularly well suited for knowledge transfer. Our initial results demonstrate that components of a
Olac Fuentes +2 more
exaly +4 more sources
An Introduction to Deep Convolutional Neural Nets for Computer Vision
Deep Learning for Medical Image Analysis, 2017R Venkaṭesh Babu
exaly +2 more sources
Evaluating Age Estimation Using Deep Convolutional Neural Nets
IS&T International Symposium on Electronic Imaging, 2017 Ignacio Arganda-Carreras
exaly +3 more sources
SRGC-Nets: Sparse Repeated Group Convolutional Neural Networks
IEEE Transactions on Neural Networks and Learning Systems, 2020Group convolution is widely used in many mobile networks to remove the filter's redundancy from the channel extent. In order to further reduce the redundancy of group convolution, this article proposes a novel repeated group convolutional (RGC) kernel, which has M primary groups, and each primary group includes N tiny groups.
Jinxing Li, Yao Lu, David Zhang
exaly +3 more sources
Wavelet J-Net: A Frequency Perspective on Convolutional Neural Networks
2021 International Joint Conference on Neural Networks (IJCNN), 2021It is well acknowledged in image processing domain that the information can be decomposed into different frequency parts and each part has its own merits. However, existing neural networks always ignore the distinctions and straightforwardly feed all the information into neural networks together, treating them equally. In this paper, we propose a novel
Linfeng Zhang 0001 +3 more
openaire +1 more source
Convolutional neural net bagging for online visual tracking
Computer Vision and Image Understanding, 2016The proposed CNN bagging method is simple yet effective.It addresses the label noise and model uncertainty problems simultaneously for CNN-based trackers.The state-of-the-art performances on 3 recent benchmarks i.e., CVPR2013, VOT2013 and TB50 illustrate the validity of the proposed algorithm.
Hanxi Li, Yi Li 0025, Fatih Porikli
openaire +2 more sources
ACM Trans. Multim. Comput. Commun. Appl.
Most state-of-the-art convolutional neural networks (CNNs) are characterized by excessive parameterization, leading to a high computational burden. Tensor decomposition has emerged as a model reduction technique for compressing deep neural networks ...
Yifan Wang +5 more
semanticscholar +1 more source
Most state-of-the-art convolutional neural networks (CNNs) are characterized by excessive parameterization, leading to a high computational burden. Tensor decomposition has emerged as a model reduction technique for compressing deep neural networks ...
Yifan Wang +5 more
semanticscholar +1 more source
Traffic Signal Control Based on Reinforcement Learning with Graph Convolutional Neural Nets
International Conference on Intelligent Transportation Systems, 2018Traffic signal control can mitigate traffic congestion and reduce travel time. A model-free reinforcement learning (RL) approach is a powerful framework for learning a responsive traffic control policy for short-term traffic demand changes without prior ...
Tomoki Nishi +3 more
semanticscholar +1 more source